Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    variable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เลย
    -0.07
     Kickstarter
    -0.07
     배송
    -0.07
    ठन
    -0.07
    _RENDERER
    -0.07
    ΕΛ
    -0.06
    _renderer
    -0.06
    .Navigate
    -0.06
     servlet
    -0.06
    PLETED
    -0.06
    POSITIVE LOGITS
     folder
    0.06
     experi
    0.06
     Stewart
    0.06
     collage
    0.06
     risen
    0.06
    iral
    0.06
     emb
    0.06
    storage
    0.06
     neben
    0.06
     Enhanced
    0.06
    Act Density 0.014%

    No Known Activations